BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230831T095746Z
LOCATION:Hall
DTSTART;TZID=Europe/Stockholm:20230627T193000
DTEND;TZID=Europe/Stockholm:20230627T213000
UID:submissions.pasc-conference.org_PASC23_sess116_pos105@linklings.com
SUMMARY:P30 - High Performance Computing Meets Approximate Bayesian Infere
nce
DESCRIPTION:Poster\n\nLisa Gaedke-Merzhäuser (Università della Svizzera it
aliana), Haavard Rue (King Abdullah University of Science and Technology),
and Olaf Schenk (Università della Svizzera italiana)\n\nDespite the ongoi
ng advancements in Bayesian computing, large-scale inference tasks continu
e to pose a computational challenge that often requires a trade-off betwee
n accuracy and computation time. Combining solution strategies from the fi
eld of high-performance computing with state-of-the-art statistical learni
ng techniques, we present a highly scalable approach for performing spatia
l-temporal Bayesian modelling based on the methodology of integrated neste
d Laplace approximations (INLA). The spatial-temporal model component is r
eformulated as the solution to a discretized stochastic partial differenti
al equation which induces sparse matrix representations for increased comp
utational efficiency. We leverage the power of today’s distributed compute
architectures by introducing a multi-level parallelism scheme throughout
the algorithm. Moreover, we rethink the computational kernel operations an
d derive GPU-accelerated linear algebra solvers for fast and reliable mode
l predictions.
END:VEVENT
END:VCALENDAR